Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    recipes use

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    殿
    0.46
     되
    0.44
    SCHRAMM
    0.44
    ूरती
    0.44
    币
    0.43
    Else
    0.42
    Quadr
    0.42
    峤
    0.42
    Transaction
    0.42
    同时也
    0.42
    POSITIVE LOGITS
    !
    0.46
    :
    0.45
     Sebelumnya
    0.45
     intérieure
    0.43
    ):
    0.42
    ’!
    0.41
     Disclaimer
    0.41
    !’
    0.41
     rapidement
    0.40
     samedi
    0.40
    Act Density 0.002%

    No Known Activations